Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Fetch information from Taiga public API for the Penpot project (id 345963) — issues, user stories, and tasks, without authentication.
.claude/skills/penpot-taiga/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -79% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 8% | 0% |
Fetch information from Taiga public API for the Penpot project (project id: 345963, slug: penpot).
No authentication required — only public project data is accessed.
Taiga — fetch them via the public API (project id 345963), no authentication needed.
python3 — the scripts/taiga.py CLI script is self-contained (stdlib only)The easiest way is to use the bundled Python script:
bash# Pass a Taiga URL directly python3 scripts/taiga.py https://tree.taiga.io/project/penpot/issue/13714 # Or use "<type> <ref>" syntax python3 scripts/taiga.py us 14128 python3 scripts/taiga.py task 13648 # Add --json for raw output python3 scripts/taiga.py --json issue 13714 # See full usage python3 scripts/taiga.py --help
Taiga web URLs follow these patterns:
| Type | Web URL Pattern | |------|----------------| | Issue | https://tree.taiga.io/project/penpot/issue/<REF> | | User Story | https://tree.taiga.io/project/penpot/us/<REF> | | Task | https://tree.taiga.io/project/penpot/task/<REF> |
To extract the type and ref from a URL:
issue/13714 → type=issue, ref=13714us/14128 → type=us, ref=14128task/13648 → type=task, ref=13648The scripts/taiga.py script wraps the Taiga API into a single convenient CLI with sensible defaults.
python3 scripts/taiga.py <taiga-url>
python3 scripts/taiga.py <type> <ref>
python3 scripts/taiga.py [--json] <taiga-url>
python3 scripts/taiga.py [--json] <type> <ref>bash# By URL (recommended — no need to think about type/ref) python3 scripts/taiga.py https://tree.taiga.io/project/penpot/issue/13714 # By type and ref python3 scripts/taiga.py us 14128 python3 scripts/taiga.py task 13648 # Raw JSON output python3 scripts/taiga.py --json issue 13714
The script prints a clean, structured summary:
textUser Story #11964 — 🔴 [DESIGN TOKENS] Typography Composite Input ================================ Status: Defining Milestone: design-systems-sprint-26 Points: 3 role(s) Assignee: Natacha Menjibar Author: Natacha Menjibar Created: 2025-09-01 Tags: iop-design-tokens URL: https://tree.taiga.io/project/penpot/us/11964 ================================ <full description text, unmodified>
The fields section includes type-specific information:
345963penpot| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,978 | 7,049 | +42% | 1 | 1 | 0% | 529 | 1,273 | +141% | 0 | 0 | — |
case-02 | fail→fail | 10,528 | 10,367 | -2% | 1 | 1 | 0% | 773 | 1,185 | +53% | 0 | 0 | — |
case-03 | fail→fail | 25,955 | 8,112 | -69% | 1 | 1 | 0% | 4,502 | 1,211 | -73% | 0 | 0 | — |
case-04 | fail→pass | 16,649 | 3,016 | -82% | 1 | 1 | 0% | 2,807 | 1,287 | -54% | 0 | 0 | — |
case-05 | fail→pass | 37,021 | 4,446 | -88% | 1 | 1 | 0% | 6,564 | 1,349 | -79% | 0 | 0 | — |
case-06 | fail→pass | 13,695 | 3,800 | -72% | 1 | 1 | 0% | 1,808 | 1,346 | -26% | 0 | 0 | — |
case-07 | pass→pass | 9,941 | 2,478 | -75% | 1 | 1 | 0% | 1,471 | 1,256 | -15% | 0 | 0 | — |
case-08 | fail→pass | 15,156 | 2,769 | -82% | 1 | 1 | 0% | 2,495 | 1,285 | -48% | 0 | 0 | — |
case-09 | pass→pass | 12,596 | 2,857 | -77% | 1 | 1 | 0% | 2,150 | 1,301 | -39% | 0 | 0 | — |
case-10 | pass→pass | 16,539 | 3,962 | -76% | 1 | 1 | 0% | 1,779 | 1,542 | -13% | 0 | 0 | — |
case-11 | pass→pass | 4,785 | 3,221 | -33% | 1 | 1 | 0% | 716 | 1,157 | +62% | 0 | 0 | — |
case-12 | pass→pass | 8,277 | 3,207 | -61% | 1 | 1 | 0% | 1,110 | 1,248 | +12% | 0 | 0 | — |
case-13 | pass→pass | 11,019 | 2,795 | -75% | 1 | 1 | 0% | 1,931 | 1,285 | -33% | 0 | 0 | — |
case-14 | pass→pass | 10,020 | 3,302 | -67% | 1 | 1 | 0% | 1,680 | 1,379 | -18% | 0 | 0 | — |
case-15 | pass→pass | 4,686 | 2,482 | -47% | 1 | 1 | 0% | 643 | 1,282 | +99% | 0 | 0 | — |
case-16 | fail→pass | 16,179 | 8,330 | -49% | 1 | 1 | 0% | 2,175 | 2,342 | +8% | 0 | 0 | — |
case-17 | pass→pass | 17,658 | 10,594 | -40% | 1 | 1 | 0% | 2,845 | 1,633 | -43% | 0 | 0 | — |
case-18 | pass→fail | 8,678 | 7,816 | -10% | 1 | 1 | 0% | 1,225 | 1,200 | -2% | 0 | 0 | — |
case-19 | pass→pass | 2,982 | 2,198 | -26% | 1 | 1 | 0% | 316 | 1,183 | +274% | 0 | 0 | — |
case-20 | fail→pass | 13,308 | 5,574 | -58% | 1 | 1 | 0% | 2,241 | 1,733 | -23% | 0 | 0 | — |
case-21 | fail→pass | 14,818 | 7,199 | -51% | 1 | 1 | 0% | 2,266 | 1,864 | -18% | 0 | 0 | — |
case-22 | fail→pass | 13,360 | 22,254 | +67% | 1 | 1 | 0% | 2,236 | 2,470 | +10% | 0 | 0 | — |
case-23 | fail→pass | 12,599 | 2,709 | -78% | 1 | 1 | 0% | 1,784 | 1,238 | -31% | 0 | 0 | — |
case-24 | fail→pass | 31,083 | 3,018 | -90% | 1 | 1 | 0% | 1,536 | 1,363 | -11% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted, and 20 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +38 percentage points is the difference between those two pass rates over the 20 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.